2023-09-12 更新
LadleNet: Translating Thermal Infrared Images to Visible Light Images Using A Scalable Two-stage U-Net
Authors:Tonghui Zou, Lei Chen
The translation of thermal infrared (TIR) images to visible light (VI) images presents a challenging task with potential applications spanning various domains such as TIR-VI image registration and fusion. Leveraging supplementary information derived from TIR image conversions can significantly enhance model performance and generalization across these applications. However, prevailing issues within this field include suboptimal image fidelity and limited model scalability. In this paper, we introduce an algorithm, LadleNet, based on the U-Net architecture. LadleNet employs a two-stage U-Net concatenation structure, augmented with skip connections and refined feature aggregation techniques, resulting in a substantial enhancement in model performance. Comprising ‘Handle’ and ‘Bowl’ modules, LadleNet’s Handle module facilitates the construction of an abstract semantic space, while the Bowl module decodes this semantic space to yield mapped VI images. The Handle module exhibits extensibility by allowing the substitution of its network architecture with semantic segmentation networks, thereby establishing more abstract semantic spaces to bolster model performance. Consequently, we propose LadleNet+, which replaces LadleNet’s Handle module with the pre-trained DeepLabv3+ network, thereby endowing the model with enhanced semantic space construction capabilities. The proposed method is evaluated and tested on the KAIST dataset, accompanied by quantitative and qualitative analyses. Compared to existing methodologies, our approach achieves state-of-the-art performance in terms of image clarity and perceptual quality. The source code will be made available at https://github.com/Ach-1914/LadleNet/tree/main/.
PDF
点此查看论文截图
MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
Authors:Ernie Chu, Tzuhsuan Huang, Shuo-Yen Lin, Jun-Cheng Chen
This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such as a normal G-buffer, or perform text-guided editing on videos captured in real-world scenarios. We employ explicit optical flows to construct a practical coding that enforces physical constraints on generated frames and mediates independent frame-wise scores. By leveraging this coding, maintaining temporal consistency in the generated videos can be framed as an optimization problem with a closed-form solution. To ensure compatibility with Stable Diffusion, we also suggest a workaround for modifying observed-space scores in latent-space Diffusion Models. Notably, MeDM does not require fine-tuning or test-time optimization of the Diffusion Models. Through extensive qualitative, quantitative, and subjective experiments on various benchmarks, the study demonstrates the effectiveness and superiority of the proposed approach. Project page can be found at https://medm2023.github.io
PDF Project page: https://medm2023.github.io
点此查看论文截图
Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection
Authors:Weijie Wang, Zhengyu Zhao, Nicu Sebe, Bruno Lepri
Malicious use of deepfakes leads to serious public concerns and reduces people’s trust in digital media. Although effective deepfake detectors have been proposed, they are substantially vulnerable to adversarial attacks. To evaluate the detector’s robustness, recent studies have explored various attacks. However, all existing attacks are limited to 2D image perturbations, which are hard to translate into real-world facial changes. In this paper, we propose adversarial head turn (AdvHeat), the first attempt at 3D adversarial face views against deepfake detectors, based on face view synthesis from a single-view fake image. Extensive experiments validate the vulnerability of various detectors to AdvHeat in realistic, black-box scenarios. For example, AdvHeat based on a simple random search yields a high attack success rate of 96.8% with 360 searching steps. When additional query access is allowed, we can further reduce the step budget to 50. Additional analyses demonstrate that AdvHeat is better than conventional attacks on both the cross-detector transferability and robustness to defenses. The adversarial images generated by AdvHeat are also shown to have natural looks. Our code, including that for generating a multi-view dataset consisting of 360 synthetic views for each of 1000 IDs from FaceForensics++, is available at https://github.com/twowwj/AdvHeaT.
PDF
点此查看论文截图
GenSelfDiff-HIS: Generative Self-Supervision Using Diffusion for Histopathological Image Segmentation
Authors:Vishnuvardhan Purma, Suhas Srinath, Seshan Srirangarajan, Aanchal Kakkar, Prathosh A. P
Histopathological image segmentation is a laborious and time-intensive task, often requiring analysis from experienced pathologists for accurate examinations. To reduce this burden, supervised machine-learning approaches have been adopted using large-scale annotated datasets for histopathological image analysis. However, in several scenarios, the availability of large-scale annotated data is a bottleneck while training such models. Self-supervised learning (SSL) is an alternative paradigm that provides some respite by constructing models utilizing only the unannotated data which is often abundant. The basic idea of SSL is to train a network to perform one or many pseudo or pretext tasks on unannotated data and use it subsequently as the basis for a variety of downstream tasks. It is seen that the success of SSL depends critically on the considered pretext task. While there have been many efforts in designing pretext tasks for classification problems, there haven’t been many attempts on SSL for histopathological segmentation. Motivated by this, we propose an SSL approach for segmenting histopathological images via generative diffusion models in this paper. Our method is based on the observation that diffusion models effectively solve an image-to-image translation task akin to a segmentation task. Hence, we propose generative diffusion as the pretext task for histopathological image segmentation. We also propose a multi-loss function-based fine-tuning for the downstream task. We validate our method using several metrics on two publically available datasets along with a newly proposed head and neck (HN) cancer dataset containing hematoxylin and eosin (H\&E) stained images along with annotations. Codes will be made public at https://github.com/PurmaVishnuVardhanReddy/GenSelfDiff-HIS.git.
PDF
点此查看论文截图
Memory Efficient Optimizers with 4-bit States
Authors:Bingrui Li, Jianfei Chen, Jun Zhu
Optimizer states are a major source of memory consumption for training neural networks, limiting the maximum trainable model within given memory budget. Compressing the optimizer states from 32-bit floating points to lower bitwidth is promising to reduce the training memory footprint, while the current lowest achievable bitwidth is 8-bit. In this work, we push optimizer states bitwidth down to 4-bit through a detailed empirical analysis of first and second moments. Specifically, we find that moments have complicated outlier patterns, that current block-wise quantization cannot accurately approximate. We use a smaller block size and propose to utilize both row-wise and column-wise information for better quantization. We further identify a zero point problem of quantizing the second moment, and solve this problem with a linear quantizer that excludes the zero point. Our 4-bit optimizer is evaluated on a wide variety of benchmarks including natural language understanding, machine translation, image classification, and instruction tuning. On all the tasks our optimizers can achieve comparable accuracy with their full-precision counterparts, while enjoying better memory efficiency.
PDF 35 pages
点此查看论文截图
DeViL: Decoding Vision features into Language
Authors:Meghal Dani, Isabel Rio-Torto, Stephan Alaniz, Zeynep Akata
Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different layers of a vision backbone have learned. Our DeViL method decodes vision features into language, not only highlighting the attribution locations but also generating textual descriptions of visual features at different layers of the network. We train a transformer network to translate individual image features of any vision layer into a prompt that a separate off-the-shelf language model decodes into natural language. By employing dropout both per-layer and per-spatial-location, our model can generalize training on image-text pairs to generate localized explanations. As it uses a pre-trained language model, our approach is fast to train, can be applied to any vision backbone, and produces textual descriptions at different layers of the vision network. Moreover, DeViL can create open-vocabulary attribution maps corresponding to words or phrases even outside the training scope of the vision model. We demonstrate that DeViL generates textual descriptions relevant to the image content on CC3M surpassing previous lightweight captioning models and attribution maps uncovering the learned concepts of the vision backbone. Finally, we show DeViL also outperforms the current state-of-the-art on the neuron-wise descriptions of the MILANNOTATIONS dataset. Code available at https://github.com/ExplainableML/DeViL
PDF Accepted at GCPR 2023 (Oral)
点此查看论文截图
Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications
Authors:Danush Kumar Venkatesh, Dominik Rivoir, Micha Pfeiffer, Fiona Kolbinger, Marius Distler, Jürgen Weitz, Stefanie Speidel
In surgical computer vision applications, obtaining labeled training data is challenging due to data-privacy concerns and the need for expert annotation. Unpaired image-to-image translation techniques have been explored to automatically generate large annotated datasets by translating synthetic images to the realistic domain. However, preserving the structure and semantic consistency between the input and translated images presents significant challenges, mainly when there is a distributional mismatch in the semantic characteristics of the domains. This study empirically investigates unpaired image translation methods for generating suitable data in surgical applications, explicitly focusing on semantic consistency. We extensively evaluate various state-of-the-art image translation models on two challenging surgical datasets and downstream semantic segmentation tasks. We find that a simple combination of structural-similarity loss and contrastive learning yields the most promising results. Quantitatively, we show that the data generated with this approach yields higher semantic consistency and can be used more effectively as training data.
PDF
点此查看论文截图
Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
Authors:Jiaxi Gu, Shicong Wang, Haoyu Zhao, Tianyi Lu, Xing Zhang, Zuxuan Wu, Songcen Xu, Wei Zhang, Yu-Gang Jiang, Hang Xu
Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and inference. A single LDM is usually only capable of generating a very limited number of video frames. Some existing works focus on separate prediction models for generating more video frames, which suffer from additional training cost and frame-level jittering, however. In this paper, we propose a framework called “Reuse and Diffuse” dubbed $\textit{VidRD}$ to produce more frames following the frames already generated by an LDM. Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process. Besides, for the autoencoder used for translation between pixel space and latent space, we inject temporal layers into its decoder and fine-tune these layers for higher temporal consistency. We also propose a set of strategies for composing video-text data that involve diverse content from multiple existing datasets including video datasets for action recognition and image-text datasets. Extensive experiments show that our method achieves good results in both quantitative and qualitative evaluations. Our project page is available $\href{https://anonymous0x233.github.io/ReuseAndDiffuse/}{here}$.
PDF
点此查看论文截图
Create Your World: Lifelong Text-to-Image Diffusion
Authors:Gan Sun, Wenqi Liang, Jiahua Dong, Jun Li, Zhengming Ding, Yang Cong
Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image translation, etc. We in this work study the problem of synthesizing instantiations of a use’s own concepts in a never-ending manner, i.e., create your world, where the new concepts from user are quickly learned with a few examples. To achieve this goal, we propose a Lifelong text-to-image Diffusion Model (L2DM), which intends to overcome knowledge “catastrophic forgetting” for the past encountered concepts, and semantic “catastrophic neglecting” for one or more concepts in the text prompt. In respect of knowledge “catastrophic forgetting”, our L2DM framework devises a task-aware memory enhancement module and a elastic-concept distillation module, which could respectively safeguard the knowledge of both prior concepts and each past personalized concept. When generating images with a user text prompt, the solution to semantic “catastrophic neglecting” is that a concept attention artist module can alleviate the semantic neglecting from concept aspect, and an orthogonal attention module can reduce the semantic binding from attribute aspect. To the end, our model can generate more faithful image across a range of continual text prompts in terms of both qualitative and quantitative metrics, when comparing with the related state-of-the-art models. The code will be released at https://wenqiliang.github.io/.
PDF 15 pages,10 figures
点此查看论文截图
Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization
Authors:Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Yadong Mu, Di Zhang, Wenwu Ou, Kun Gai
Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to data across several modalities. The prevailing approaches primarily regard visual input as the prompt and focus exclusively on optimizing the text generation process conditioned upon vision content by a frozen LLM. Such an inequitable treatment of vision and language heavily constrains the model’s potential. In this paper, we break through this limitation by representing both vision and language in a unified representation. To this end, we craft a visual tokenizer that translates the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image content. Coped with this visual tokenizer, the presented foundation model called LaVIT (Language-VIsion Transformer) can handle both image and text indiscriminately under a unified generative learning paradigm. Pre-trained on the web-scale image-text corpus, LaVIT is empowered with impressive multi-modal comprehension capability. The extensive experiments showcase that it outperforms existing models by a large margin on downstream tasks. Our code and models will be available at https://github.com/jy0205/LaVIT.
PDF
点此查看论文截图