2023-09-12 更新
Contrastive Feature Masking Open-Vocabulary Vision Transformer
Authors:Dahun Kim, Anelia Angelova, Weicheng Kuo
We present Contrastive Feature Masking Vision Transformer (CFM-ViT) - an image-text pretraining methodology that achieves simultaneous learning of image- and region-level representation for open-vocabulary object detection (OVD). Our approach combines the masked autoencoder (MAE) objective into the contrastive learning objective to improve the representation for localization tasks. Unlike standard MAE, we perform reconstruction in the joint image-text embedding space, rather than the pixel space as is customary with the classical MAE method, which causes the model to better learn region-level semantics. Moreover, we introduce Positional Embedding Dropout (PED) to address scale variation between image-text pretraining and detection finetuning by randomly dropping out the positional embeddings during pretraining. PED improves detection performance and enables the use of a frozen ViT backbone as a region classifier, preventing the forgetting of open-vocabulary knowledge during detection finetuning. On LVIS open-vocabulary detection benchmark, CFM-ViT achieves a state-of-the-art 33.9 AP$r$, surpassing the best approach by 7.6 points and achieves better zero-shot detection transfer. Finally, CFM-ViT acquires strong image-level representation, outperforming the state of the art on 8 out of 12 metrics on zero-shot image-text retrieval benchmarks.
PDF Accepted to ICCV 2023
点此查看论文截图
Contrastive Grouping with Transformer for Referring Image Segmentation
Authors:Jiajin Tang, Ge Zheng, Cheng Shi, Sibei Yang
Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classification frameworks, which attempt straightforwardly to align vision and language at the pixel level, thus failing to capture critical object-level information. In this paper, we propose a mask classification framework, Contrastive Grouping with Transformer network (CGFormer), which explicitly captures object-level information via token-based querying and grouping strategy. Specifically, CGFormer first introduces learnable query tokens to represent objects and then alternately queries linguistic features and groups visual features into the query tokens for object-aware cross-modal reasoning. In addition, CGFormer achieves cross-level interaction by jointly updating the query tokens and decoding masks in every two consecutive layers. Finally, CGFormer cooperates contrastive learning to the grouping strategy to identify the token and its mask corresponding to the referent. Experimental results demonstrate that CGFormer outperforms state-of-the-art methods in both segmentation and generalization settings consistently and significantly.
PDF Accepted by CVPR 2023
点此查看论文截图
CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning
Authors:Hongyu Hu, Jiyuan Zhang, Minyi Zhao, Zhenbang Sun
Nowadays, the research on Large Vision-Language Models (LVLMs) has been significantly promoted thanks to the success of Large Language Models (LLM). Nevertheless, these Vision-Language Models (VLMs) are suffering from the drawback of hallucination — due to insufficient understanding of vision and language modalities, VLMs may generate incorrect perception information when doing downstream applications, for example, captioning a non-existent entity. To address the hallucination phenomenon, on the one hand, we introduce a Contrastive Instruction Evaluation Method (CIEM), which is an automatic pipeline that leverages an annotated image-text dataset coupled with an LLM to generate factual/contrastive question-answer pairs for the evaluation of the hallucination of VLMs. On the other hand, based on CIEM, we further propose a new instruction tuning method called CIT (the abbreviation of Contrastive Instruction Tuning) to alleviate the hallucination of VLMs by automatically producing high-quality factual/contrastive question-answer pairs and corresponding justifications for model tuning. Through extensive experiments on CIEM and CIT, we pinpoint the hallucination issues commonly present in existing VLMs, the disability of the current instruction-tuning dataset to handle the hallucination phenomenon and the superiority of CIT-tuned VLMs over both CIEM and public datasets.
PDF
点此查看论文截图
Unsupervised Gaze-aware Contrastive Learning with Subject-specific Condition
Authors:Lingyu Du, Xucong Zhang, Guohao Lan
Appearance-based gaze estimation has shown great promise in many applications by using a single general-purpose camera as the input device. However, its success is highly depending on the availability of large-scale well-annotated gaze datasets, which are sparse and expensive to collect. To alleviate this challenge we propose ConGaze, a contrastive learning-based framework that leverages unlabeled facial images to learn generic gaze-aware representations across subjects in an unsupervised way. Specifically, we introduce the gaze-specific data augmentation to preserve the gaze-semantic features and maintain the gaze consistency, which are proven to be crucial for effective contrastive gaze representation learning. Moreover, we devise a novel subject-conditional projection module that encourages a share feature extractor to learn gaze-aware and generic representations. Our experiments on three public gaze estimation datasets show that ConGaze outperforms existing unsupervised learning solutions by 6.7% to 22.5%; and achieves 15.1% to 24.6% improvement over its supervised learning-based counterpart in cross-dataset evaluations.
PDF
点此查看论文截图