2022-11-22 更新
PointCLIP V2: Adapting CLIP for Powerful 3D Open-world Learning
Authors:Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyao Zeng, Shanghang Zhang, Peng Gao
Contrastive Language-Image Pre-training (CLIP) has shown promising open-world performance on 2D image tasks, while its transferred capacity on 3D point clouds, i.e., PointCLIP, is still far from satisfactory. In this work, we propose PointCLIP V2, a powerful 3D open-world learner, to fully unleash the potential of CLIP on 3D point cloud data. First, we introduce a realistic shape projection module to generate more realistic depth maps for CLIP’s visual encoder, which is quite efficient and narrows the domain gap between projected point clouds with natural images. Second, we leverage large-scale language models to automatically design a more descriptive 3D-semantic prompt for CLIP’s textual encoder, instead of the previous hand-crafted one. Without introducing any training in 3D domains, our approach significantly surpasses PointCLIP by +42.90%, +40.44%, and +28.75% accuracy on three datasets for zero-shot 3D classification. Furthermore, PointCLIP V2 can be extended to few-shot classification, zero-shot part segmentation, and zero-shot 3D object detection in a simple manner, demonstrating our superior generalization ability for 3D open-world learning. Code will be available at https://github.com/yangyangyang127/PointCLIP_V2.
PDF
点此查看论文截图
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
Authors:Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang, Rynson W. H. Lau, Wanli Ouyang, Wangmeng Zuo
Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vision. PointCLIP converts point cloud data to multi-view depth maps, adopting CLIP for shape classification. However, its performance is restricted by the domain gap between rendered depth maps and images, as well as the diversity of depth distributions. To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification. We introduce a new depth rendering setting that forms a better visual effect, and then render 52,460 pairs of images and depth maps from ShapeNet for pre-training. The pre-training scheme of CLIP2Point combines cross-modality learning to enforce the depth features for capturing expressive visual and textual features and intra-modality learning to enhance the invariance of depth aggregation. Additionally, we propose a novel Dual-Path Adapter (DPA) module, i.e., a dual-path structure with simplified adapters for few-shot learning. The dual-path structure allows the joint use of CLIP and CLIP2Point, and the simplified adapter can well fit few-shot tasks without post-search. Experimental results show that CLIP2Point is effective in transferring CLIP knowledge to 3D vision. Our CLIP2Point outperforms PointCLIP and other self-supervised 3D networks, achieving state-of-the-art results on zero-shot and few-shot classification.
PDF
点此查看论文截图
Multitask Vision-Language Prompt Tuning
Authors:Sheng Shen, Shijia Yang, Tianjun Zhang, Bohan Zhai, Joseph E. Gonzalez, Kurt Keutzer, Trevor Darrell
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.
PDF arXiv admin note: text overlap with arXiv:2203.05557 by other authors
点此查看论文截图
Ask Me Anything: A simple strategy for prompting language models
Authors:Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré
Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training. Prompting is a brittle process wherein small modifications to the prompt can cause large variations in the model predictions, and therefore significant effort is dedicated towards designing a painstakingly “perfect prompt” for a task. To mitigate the high degree of effort involved in prompt-design, we instead ask whether producing multiple effective, yet imperfect, prompts and aggregating them can lead to a high quality prompting strategy. Our observations motivate our proposed prompting method, ASK ME ANYTHING (AMA). We first develop an understanding of the effective prompt formats, finding that question-answering (QA) prompts, which encourage open-ended generation (“Who went to the park?”) tend to outperform those that restrict the model outputs (“John went to the park. Output True or False.”). Our approach recursively uses the LLM itself to transform task inputs to the effective QA format. We apply the collected prompts to obtain several noisy votes for the input’s true label. We find that the prompts can have very different accuracies and complex dependencies and thus propose to use weak supervision, a procedure for combining the noisy predictions, to produce the final predictions for the inputs. We evaluate AMA across open-source model families (e.g., EleutherAI, BLOOM, OPT, and T0) and model sizes (125M-175B parameters), demonstrating an average performance lift of 10.2% over the few-shot baseline. This simple strategy enables the open-source GPT-J-6B model to match and exceed the performance of few-shot GPT3-175B on 15 of 20 popular benchmarks. Averaged across these tasks, the GPT-J-6B model outperforms few-shot GPT3-175B. We release our code here: https://github.com/HazyResearch/ama_prompting
PDF
点此查看论文截图
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Authors:Jianing Wang, Chengcheng Han, Chengyu Wang, Chuanqi Tan, Minghui Qiu, Songfang Huang, Jun Huang, Ming Gao
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.
PDF
点此查看论文截图
UniSumm: Unified Few-shot Summarization with Multi-Task Pre-Training and Prefix-Tuning
Authors:Yulong Chen, Yang Liu, Ruochen Xu, Ziyi Yang, Chenguang Zhu, Michael Zeng, Yue Zhang
The diverse demands of different summarization tasks and their high annotation costs are driving a need for few-shot summarization. However, despite the emergence of many summarization tasks and datasets, the current training paradigm for few-shot summarization systems ignores potentially shareable knowledge in heterogeneous datasets. To this end, we propose \textsc{UniSumm}, a unified few-shot summarization model pre-trained with multiple summarization tasks and can be prefix-tuned to excel at any few-shot summarization datasets. Meanwhile, to better evaluate few-shot summarization systems, under the principles of diversity and robustness, we assemble and publicize a new benchmark \textsc{SummZoo}. It consists of $8$ diverse summarization tasks with multiple sets of few-shot samples for each task, covering both monologue and dialogue domains. Experimental results and ablation studies show that \textsc{UniSumm} outperforms strong baseline systems by a large margin across all tasks in \textsc{SummZoo} under both automatic and human evaluations. We release our code and benchmark at \url{https://github.com/microsoft/UniSumm}.
PDF
点此查看论文截图
Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization
Authors:David Adams, Gandharv Suri, Yllias Chali
In Natural Language Processing, multi-document summarization (MDS) poses many challenges to researchers above those posed by single-document summarization (SDS). These challenges include the increased search space and greater potential for the inclusion of redundant information. While advancements in deep learning approaches have led to the development of several advanced language models capable of summarization, the variety of training data specific to the problem of MDS remains relatively limited. Therefore, MDS approaches which require little to no pretraining, known as few-shot or zero-shot applications, respectively, could be beneficial additions to the current set of tools available in summarization. To explore one possible approach, we devise a strategy for combining state-of-the-art models’ outputs using maximal marginal relevance (MMR) with a focus on query relevance rather than document diversity. Our MMR-based approach shows improvement over some aspects of the current state-of-the-art results in both few-shot and zero-shot MDS applications while maintaining a state-of-the-art standard of output by all available metrics.
PDF
点此查看论文截图
Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization
Authors:Mengmeng Xu, Yanghao Li, Cheng-Yang Fu, Bernard Ghanem, Tao Xiang, Juan-Manuel Perez-Rua
This paper deals with the problem of localizing objects in image and video datasets from visual exemplars. In particular, we focus on the challenging problem of egocentric visual query localization. We first identify grave implicit biases in current query-conditioned model design and visual query datasets. Then, we directly tackle such biases at both frame and object set levels. Concretely, our method solves these issues by expanding limited annotations and dynamically dropping object proposals during training. Additionally, we propose a novel transformer-based module that allows for object-proposal set context to be considered while incorporating query information. We name our module Conditioned Contextual Transformer or CocoFormer. Our experiments show the proposed adaptations improve egocentric query detection, leading to a better visual query localization system in both 2D and 3D configurations. Thus, we are able to improve frame-level detection performance from 26.28% to 31.26 in AP, which correspondingly improves the VQ2D and VQ3D localization scores by significant margins. Our improved context-aware query object detector ranked first and second in the VQ2D and VQ3D tasks in the 2nd Ego4D challenge. In addition to this, we showcase the relevance of our proposed model in the Few-Shot Detection (FSD) task, where we also achieve SOTA results. Our code is available at https://github.com/facebookresearch/vq2d_cvpr.
PDF We ranked first and second in the VQ2D and VQ3D tasks in the 2nd Ego4D challenge
点此查看论文截图
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Authors:Xu Zhang, Wen Wang, Zhe Chen, Yufei Xu, Jing Zhang, Dacheng Tao
Animal pose estimation is challenging for existing image-based methods because of limited training data and large intra- and inter-species variances. Motivated by the progress of visual-language research, we propose that pre-trained language models (e.g., CLIP) can facilitate animal pose estimation by providing rich prior knowledge for describing animal keypoints in text. However, we found that building effective connections between pre-trained language models and visual animal keypoints is non-trivial since the gap between text-based descriptions and keypoint-based visual features about animal pose can be significant. To address this issue, we introduce a novel prompt-based Contrastive learning scheme for connecting Language and AniMal Pose (CLAMP) effectively. The CLAMP attempts to bridge the gap by adapting the text prompts to the animal keypoints during network training. The adaptation is decomposed into spatial-aware and feature-aware processes, and two novel contrastive losses are devised correspondingly. In practice, the CLAMP enables a new cross-modal animal pose estimation paradigm. Experimental results show that our method achieves state-of-the-art performance under the supervised, few-shot, and zero-shot settings, outperforming image-based methods by a large margin. The source code will be made publicly available.
PDF
点此查看论文截图
Knowledge Graph Refinement based on Triplet BERT-Networks
Authors:Armita Khajeh Nassiri, Nathalie Pernelle, Fatiha Sais, Gianluca Quercini
Knowledge graph embedding techniques are widely used for knowledge graph refinement tasks such as graph completion and triple classification. These techniques aim at embedding the entities and relations of a Knowledge Graph (KG) in a low dimensional continuous feature space. This paper adopts a transformer-based triplet network creating an embedding space that clusters the information about an entity or relation in the KG. It creates textual sequences from facts and fine-tunes a triplet network of pre-trained transformer-based language models. It adheres to an evaluation paradigm that relies on an efficient spatial semantic search technique. We show that this evaluation protocol is more adapted to a few-shot setting for the relation prediction task. Our proposed GilBERT method is evaluated on triplet classification and relation prediction tasks on multiple well-known benchmark knowledge graphs such as FB13, WN11, and FB15K. We show that GilBERT achieves better or comparable results to the state-of-the-art performance on these two refinement tasks.
PDF Accepted and presented at the DeepOntoNLP Workshop of the ESWC 2022 conference
点此查看论文截图
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
Authors:Xiangyu Peng, Chen Xing, Prafulla Kumar Choubey, Chien-Sheng Wu, Caiming Xiong
Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model tuning. However, with limited training samples in few-shot settings, prompt tuning fails to match the performance of full-model fine-tuning. In this work, we focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. Recognizing the good generalization capabilities of ensemble methods in low-data regime, we first experiment and show that a simple ensemble of model predictions based on different source prompts, outperforms existing multi-prompt knowledge transfer approaches such as source prompt fusion in the few-shot setting. Motivated by this observation, we further investigate model ensembles and propose Sample-specific Ensemble of Source Models (SESoM). SESoM learns to adjust the contribution of each source model for each target sample separately when ensembling source model outputs. Through this way, SESoM inherits the superior generalization of model ensemble approaches and simultaneously captures the sample-specific competence of each source prompt. We conduct experiments across a diverse set of eight NLP tasks using models of different scales (T5-{base, large, XL}) and find that SESoM consistently outperforms the existing models of the same as well as larger parametric scale by a large margin.
PDF
点此查看论文截图