Abstract:Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant computational resources. This paper proposes an efficient time step sampling method based on an image spectral analysis of the diffusion process, aimed at optimizing the denoising process. Instead of the traditional uniform distribution-based time step sampling, we introduce a Beta distribution-like sampling technique that prioritizes critical steps in the early and late stages of the process. Our hypothesis is that certain steps exhibit significant changes in image content, while others contribute minimally. We validated our approach using Fourier transforms to measure frequency response changes at each step, revealing substantial low-frequency changes early on and high-frequency adjustments later. Experiments with ADM and Stable Diffusion demonstrated that our Beta Sampling method consistently outperforms uniform sampling, achieving better FID and IS scores, and offers competitive efficiency relative to state-of-the-art methods like AutoDiffusion. This work provides a practical framework for enhancing diffusion model efficiency by focusing computational resources on the most impactful steps, with potential for further optimization and broader application.
Abstract:In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an Audio-Visual Captioning framework, a simple yet powerful baseline approach applicable to audio-visual captioning. AVCap utilizes audio-visual features as text tokens, which has many advantages not only in performance but also in the extensibility and scalability of the model. AVCap is designed around three pivotal dimensions: the exploration of optimal audio-visual encoder architectures, the adaptation of pre-trained models according to the characteristics of generated text, and the investigation into the efficacy of modality fusion in captioning. Our method outperforms existing audio-visual captioning methods across all metrics and the code is available on https://github.com/JongSuk1/AVCap
Abstract:Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text alignment. This paper explores the intricate relationship between compositionality and recognition -- two pivotal aspects of VLM capability. We conduct a comprehensive evaluation of existing VLMs, covering both pre-training approaches aimed at recognition and the fine-tuning methods designed to improve compositionality. Our evaluation employs 12 benchmarks for compositionality, along with 21 zero-shot classification and two retrieval benchmarks for recognition. In our analysis from 274 CLIP model checkpoints, we reveal patterns and trade-offs that emerge between compositional understanding and recognition accuracy. Ultimately, this necessitates strategic efforts towards developing models that improve both capabilities, as well as the meticulous formulation of benchmarks for compositionality. We open our evaluation framework at https://github.com/ytaek-oh/vl_compo.
Abstract:There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean samples are from two different domains, a common practice in prior works is to adopt Dual BN, where BN and BN are used for adversarial and clean branches, respectively. A popular belief for motivating Dual BN is that estimating normalization statistics of this mixture distribution is challenging and thus disentangling it for normalization achieves stronger robustness. In contrast to this belief, we reveal that disentangling statistics plays a less role than disentangling affine parameters in model training. This finding aligns with prior work (Rebuffi et al., 2023), and we build upon their research for further investigations. We demonstrate that the domain gap between adversarial and clean samples is not very large, which is counter-intuitive considering the significant influence of adversarial perturbation on the model accuracy. We further propose a two-task hypothesis which serves as the empirical foundation and a unified framework for Hybrid-AT improvement. We also investigate Dual BN in test-time and reveal that affine parameters characterize the robustness during inference. Overall, our work sheds new light on understanding the mechanism of Dual BN in Hybrid-AT and its underlying justification.
Abstract:We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those robustness benchmarks are restricted in specified variations and have low synthetic quality. In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness. Leveraging diffusion models, we are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Experimental results show that ImageNet-D results in a significant accuracy drop to a range of vision models, from the standard ResNet visual classifier to the latest foundation models like CLIP and MiniGPT-4, significantly reducing their accuracy by up to 60\%. Our work suggests that diffusion models can be an effective source to test vision models. The code and dataset are available at https://github.com/chenshuang-zhang/imagenet_d.
Abstract:Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, facilitated by a shared attention-based transformation predictor. It enables the aggregation of features from diverse augmentations into a representative embedding, providing robust supervision. Notably, this is achieved with minimal computational overhead. Extensive ablation studies and qualitative results verify the effectiveness of our method. EquiAV outperforms previous works across various audio-visual benchmarks.
Abstract:In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-based stereo-confidence networks should be trained with ground truth (GT), which is not feasible in a self-supervised setting. In this paper, we propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps by checking their consistency without the need for GT and a training process. Experimental results show that the proposed method outperforms the previous methods and works well on various configurations by filtering out erroneous areas where the stereo-matching is vulnerable, especially such as textureless regions, occlusion boundaries, and reflective surfaces.
Abstract:We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems. Grounded in the foundational concepts of disparity definition and the disparity plane sweep, the proposed stereo-confidence method is built upon the idea that any shift in a stereo-image pair should be updated in a corresponding amount shift in the disparity map. Based on this idea, the proposed stereo-confidence method can be summarized in three folds. 1) Using the disparity plane sweep, multiple disparity maps can be obtained and treated as a 3-D volume (predicted disparity volume), like the cost volume is constructed. 2) One of these disparity maps serves as an anchor, allowing us to define a desirable (or ideal) disparity profile at every spatial point. 3) By comparing the desirable and predicted disparity profiles, we can quantify the level of matching ambiguity between left and right images for confidence measurement. Extensive experimental results using various stereo-matching networks and datasets demonstrate that the proposed stereo-confidence method not only shows competitive performance on its own but also consistent performance improvements when it is used as an input modality for learning-based stereo-confidence methods.
Abstract:While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial manufacturing contexts. Recently, image mixing-based methods have been introduced, exhibiting improved performance on public benchmark datasets. However, their application to industrial tasks remains challenging. The manufacturing environment generates massive amounts of unlabeled data on a daily basis, with only a few instances of abnormal data occurrences. This leads to severe data imbalance. Thus, creating well-balanced datasets is not straightforward due to the high costs associated with labeling. Nonetheless, this is a crucial step for enhancing productivity. For this reason, we introduce ContextMix, a method tailored for industrial applications and benchmark datasets. ContextMix generates novel data by resizing entire images and integrating them into other images within the batch. This approach enables our method to learn discriminative features based on varying sizes from resized images and train informative secondary features for object recognition using occluded images. With the minimal additional computation cost of image resizing, ContextMix enhances performance compared to existing augmentation techniques. We evaluate its effectiveness across classification, detection, and segmentation tasks using various network architectures on public benchmark datasets. Our proposed method demonstrates improved results across a range of robustness tasks. Its efficacy in real industrial environments is particularly noteworthy, as demonstrated using the passive component dataset.
Abstract:Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotation-equivariance remains an elusive goal. Current detectors deploy various alignment techniques to derive rotation-invariant features, but still rely on high capacity models and heavy data augmentation with all possible rotations. In this paper, we introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED), whose entire process from the image to the bounding box prediction is strictly equivariant. Specifically, we decouple the invariant task (object classification) and the equivariant task (object localization) to achieve end-to-end equivariance. We represent the bounding box as a set of rotation-equivariant vectors to implement rotation-equivariant localization. Moreover, we utilized these rotation-equivariant vectors as offsets in the deformable convolution, thereby enhancing the existing advantages of spatial adaptation. Leveraging full rotation-equivariance, our FRED demonstrates higher robustness to image-level rotation compared to existing methods. Furthermore, we show that FRED is one step closer to non-axis aligned learning through our experiments. Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.