Siwei Yang

Bingchen Zhao, Jiahao Wang, Wufei Ma et al.

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on synthetic data or ignore the effects of individual nuisance factors. We introduce OOD-CV-v2, a benchmark dataset that includes out-of-distribution examples of 10 object categories in terms of pose, shape, texture, context and the weather conditions, and enables benchmarking of models for image classification, object detection, and 3D pose estimation. In addition to this novel dataset, we contribute extensive experiments using popular baseline methods, which reveal that: 1) Some nuisance factors have a much stronger negative effect on the performance compared to others, also depending on the vision task. 2) Current approaches to enhance robustness have only marginal effects, and can even reduce robustness. 3) We do not observe significant differences between convolutional and transformer architectures. We believe our dataset provides a rich test bed to study robustness and will help push forward research in this area. Our dataset can be accessed from https://bzhao.me/OOD-CV/

Siwei Yang, Longlong Jing, Junfei Xiao et al.

The weakly supervised instance segmentation is a challenging task. The existing methods typically use bounding boxes as supervision and optimize the network with a regularization loss term such as pairwise color affinity loss for instance segmentation. Through systematic analysis, we found that the commonly used pairwise affinity loss has two limitations: (1) it works with color affinity but leads to inferior performance with other modalities such as depth gradient, (2)the original affinity loss does not prevent trivial predictions as intended but actually accelerates this process due to the affinity loss term being symmetric. To overcome these two limitations, in this paper, we propose a novel asymmetric affinity loss which provides the penalty against the trivial prediction and generalizes well with affinity loss from different modalities. With the proposed asymmetric affinity loss, our method outperforms the state-of-the-art methods on the Cityscapes dataset and outperforms our baseline method by 3.5% in mask AP.

Yunfei Xie, Juncheng Wu, Haoqin Tu et al.

Large language models (LLMs) have exhibited remarkable capabilities across various domains and tasks, pushing the boundaries of our knowledge in learning and cognition. The latest model, OpenAI's o1, stands out as the first LLM with an internalized chain-of-thought technique using reinforcement learning strategies. While it has demonstrated surprisingly strong capabilities on various general language tasks, its performance in specialized fields such as medicine remains unknown. To this end, this report provides a comprehensive exploration of o1 on different medical scenarios, examining 3 key aspects: understanding, reasoning, and multilinguality. Specifically, our evaluation encompasses 6 tasks using data from 37 medical datasets, including two newly constructed and more challenging question-answering (QA) tasks based on professional medical quizzes from the New England Journal of Medicine (NEJM) and The Lancet. These datasets offer greater clinical relevance compared to standard medical QA benchmarks such as MedQA, translating more effectively into real-world clinical utility. Our analysis of o1 suggests that the enhanced reasoning ability of LLMs may (significantly) benefit their capability to understand various medical instructions and reason through complex clinical scenarios. Notably, o1 surpasses the previous GPT-4 in accuracy by an average of 6.2% and 6.6% across 19 datasets and two newly created complex QA scenarios. But meanwhile, we identify several weaknesses in both the model capability and the existing evaluation protocols, including hallucination, inconsistent multilingual ability, and discrepant metrics for evaluation. We release our raw data and model outputs at https://ucsc-vlaa.github.io/o1_medicine/ for future research.

Yixin Fei, Zhongkai Zhao, Siwei Yang et al.

We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the unlabeled images could contain both seen classes and unseen classes. The seen classes can be seen as an implicit criterion of classes, which makes this setting different from unsupervised clustering where the cluster criteria may be ambiguous. We mainly concern the problem of discovering categories within a fine-grained dataset since it is one of the most direct applications of category discovery, i.e. helping experts discover novel concepts within an unlabeled dataset using the implicit criterion set forth by the seen classes. State-of-the-art methods for generalized category discovery leverage contrastive learning to learn the representations, but the large inter-class similarity and intra-class variance pose a challenge for the methods because the negative examples may contain irrelevant cues for recognizing a category so the algorithms may converge to a local-minima. We present a novel method called Expert-Contrastive Learning (XCon) to help the model to mine useful information from the images by first partitioning the dataset into sub-datasets using k-means clustering and then performing contrastive learning on each of the sub-datasets to learn fine-grained discriminative features. Experiments on fine-grained datasets show a clear improved performance over the previous best methods, indicating the effectiveness of our method.

Siwei Yang, Hanrong Ye, Dan Xu

This paper targets the problem of multi-task dense prediction which aims to achieve simultaneous learning and inference on a bunch of multiple dense prediction tasks in a single framework. A core objective in design is how to effectively model cross-task interactions to achieve a comprehensive improvement on different tasks based on their inherent complementarity and consistency. Existing works typically design extra expensive distillation modules to perform explicit interaction computations among different task-specific features in both training and inference, bringing difficulty in adaptation for different task sets, and reducing efficiency due to clearly increased size of multi-task models. In contrast, we introduce feature-wise contrastive consistency into modeling the cross-task interactions for multi-task dense prediction. We propose a novel multi-task contrastive regularization method based on the consistency to effectively boost the representation learning of the different sub-tasks, which can also be easily generalized to different multi-task dense prediction frameworks, and costs no additional computation in the inference. Extensive experiments on two challenging datasets (i.e. NYUD-v2 and Pascal-Context) clearly demonstrate the superiority of the proposed multi-task contrastive learning approach for dense predictions, establishing new state-of-the-art performances.

Yuhan Wang, Siwei Yang, Bingchen Zhao et al.

Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular image-editing datasets: OmniEdit, HQ-Edit, and UltraEdit. Specifically, our methodology involves 1) regenerating output images to enhance visual quality and instruction alignment, and 2) selectively rewriting prompts to improve semantic clarity. To validate the efficacy of our dataset, we fine-tune advanced open-source models on GPT-IMAGE-EDIT-1.5M. The empirical results are exciting, e.g., the fine-tuned FluxKontext achieves highly competitive performance across a comprehensive suite of benchmarks, including 7.24 on GEdit-EN, 3.80 on ImgEdit-Full, and 8.78 on Complex-Edit, showing stronger instruction following and higher perceptual quality while maintaining identity. These scores markedly exceed all previously published open-source methods and substantially narrow the gap to leading proprietary models. We hope the full release of GPT-IMAGE-EDIT-1.5M can help to catalyze further open research in instruction-guided image editing.

Shiqiao Meng, Zonglin Di, Siwei Yang et al.

Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and require pixel-level labeling, which is tedious and error-prone. To make matters worse, the earth has a diverse range of terrain, vegetation, and man-made objects. It is well known that models trained in one area generalize poorly to other areas. Various shooting conditions such as light and angel, as well as different image processing techniques further complicate the issue. It is impractical to develop training data to cover all image styles. This paper proposes to leverage OpenStreetMap road data as weak labels and large scale satellite imagery to pre-train semantic segmentation models. Our extensive experimental results show that the prediction accuracy increases with the amount of the weakly labeled data, as well as the road density in the areas chosen for training. Using as much as 100 times more data than the widely used DeepGlobe road dataset, our model with the D-LinkNet architecture and the ResNet-50 backbone exceeds the top performer of the current DeepGlobe leaderboard. Furthermore, due to large-scale pre-training, our model generalizes much better than those trained with only the curated datasets, implying great application potential.

Siwei Yang, Mude Hui, Bingchen Zhao et al.

We introduce $\texttt{Complex-Edit}$, a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity. To develop this benchmark, we harness GPT-4o to automatically collect a diverse set of editing instructions at scale. Our approach follows a well-structured ``Chain-of-Edit'' pipeline: we first generate individual atomic editing tasks independently and then integrate them to form cohesive, complex instructions. Additionally, we introduce a suite of metrics to assess various aspects of editing performance, along with a VLM-based auto-evaluation pipeline that supports large-scale assessments. Our benchmark yields several notable insights: 1) Open-source models significantly underperform relative to proprietary, closed-source models, with the performance gap widening as instruction complexity increases; 2) Increased instructional complexity primarily impairs the models' ability to retain key elements from the input images and to preserve the overall aesthetic quality; 3) Decomposing a complex instruction into a sequence of atomic steps, executed in a step-by-step manner, substantially degrades performance across multiple metrics; 4) A straightforward Best-of-N selection strategy improves results for both direct editing and the step-by-step sequential approach; and 5) We observe a ``curse of synthetic data'': when synthetic data is involved in model training, the edited images from such models tend to appear increasingly synthetic as the complexity of the editing instructions rises -- a phenomenon that intriguingly also manifests in the latest GPT-4o outputs.

Siwei Yang, Bingchen Zhao, Cihang Xie

This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts, such as depth-first search (DFS). The key feature of our evaluation benchmark lies in its interactive evaluation protocol - for example, in DFS, the availability of each node's connected edge is contingent upon the model's traversal to that node, thereby necessitating the LLM's ability to effectively remember visited nodes and strategize subsequent moves considering the possible environmental feedback in the future steps. We comprehensively build AQA-Bench with three different algorithms, namely binary search, depth-first search, and breadth-first search, and to evaluate the sequential reasoning ability of 14 different LLMs. Our investigations reveal several interesting findings: (1) Closed-source models like GPT-4 and Gemini generally show much stronger sequential reasoning ability, significantly outperforming open-source LLMs. (2) Naively providing in-context examples may inadvertently hurt few-shot performance in an interactive environment due to over-fitting to examples. (3) Instead of using optimal steps from another test case as the in-context example, a very limited number of predecessor steps in the current test case following the optimal policy can substantially boost small models' performance. (4) The performance gap between weak models and strong models is greatly due to the incapability of weak models to start well. (5) The scaling correlation between performance and model size is not always significant, sometimes even showcasing an inverse trend. We hope our study can catalyze future work on advancing the understanding and enhancement of LLMs' capabilities in sequential reasoning. The code is available at https://github.com/UCSC-VLAA/AQA-Bench.

Mude Hui, Siwei Yang, Bingchen Zhao et al.

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose two evaluation metrics, Alignment and Coherence, to quantitatively assess the quality of image edit pairs using GPT-4V. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models. For example, an HQ-Edit finetuned InstructPix2Pix can attain state-of-the-art image editing performance, even surpassing those models fine-tuned with human-annotated data. The project page is https://thefllood.github.io/HQEdit_web.

Siwei Yang, Xianhang Li, Jieru Mei et al.

Segmenting brain tumors is complex due to their diverse appearances and scales. Brain metastases, the most common type of brain tumor, are a frequent complication of cancer. Therefore, an effective segmentation model for brain metastases must adeptly capture local intricacies to delineate small tumor regions while also integrating global context to understand broader scan features. The TransUNet model, which combines Transformer self-attention with U-Net's localized information, emerges as a promising solution for this task. In this report, we address brain metastases segmentation by training the 3D-TransUNet model on the Brain Tumor Segmentation (BraTS-METS) 2023 challenge dataset. Specifically, we explored two architectural configurations: the Encoder-only 3D-TransUNet, employing Transformers solely in the encoder, and the Decoder-only 3D-TransUNet, utilizing Transformers exclusively in the decoder. For Encoder-only 3D-TransUNet, we note that Masked-Autoencoder pre-training is required for a better initialization of the Transformer Encoder and thus accelerates the training process. We identify that the Decoder-only 3D-TransUNet model should offer enhanced efficacy in the segmentation of brain metastases, as indicated by our 5-fold cross-validation on the training set. However, our use of the Encoder-only 3D-TransUNet model already yield notable results, with an average lesion-wise Dice score of 59.8\% on the test set, securing second place in the BraTS-METS 2023 challenge.

Tony Lee, Haoqin Tu, Chi Heem Wong et al. · stanford

Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE, which evaluates the ALMs on avoiding stereotypes, and CoRe-Bench, which measures reasoning over conversational audio through inferential multi-turn question answering -- to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs: audio perception, knowledge, reasoning, emotion detection, bias, fairness, multilinguality, robustness, toxicity, and safety. We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models. We test 14 open-weight and closed-API ALMs from 3 developers and 3 additional simple baseline systems each consisting of an automatic speech recognizer and a language model. Our results show that while Gemini 2.5 Pro ranks top in 5 out of 10 aspects, it exhibits group unfairness ($p=0.01$) on ASR tasks whereas most of the other models do not. We also find that the baseline systems perform reasonably well on AHELM, with one ranking 6th overall despite having only speech-to-text capabilities. For transparency, all raw prompts, model generations, and outputs are available on our website at https://crfm.stanford.edu/helm/audio/v1.0.0. AHELM is intended to be a living benchmark and new datasets and models will be added over time.

Luis Burbano, Diego Ortiz, Qi Sun et al.

Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to novel real-world situations. These capabilities, however, also create new security risks. In this paper, we introduce CHAI (Command Hijacking against embodied AI), a new class of prompt-based attacks that exploit the multimodal language interpretation abilities of Large Visual-Language Models (LVLMs). CHAI embeds deceptive natural language instructions, such as misleading signs, in visual input, systematically searches the token space, builds a dictionary of prompts, and guides an attacker model to generate Visual Attack Prompts. We evaluate CHAI on four LVLM agents; drone emergency landing, autonomous driving, and aerial object tracking, and on a real robotic vehicle. Our experiments show that CHAI consistently outperforms state-of-the-art attacks. By exploiting the semantic and multimodal reasoning strengths of next-generation embodied AI systems, CHAI underscores the urgent need for defenses that extend beyond traditional adversarial robustness.

Zihao Zhang, Shaozuo Yu, Siwei Yang et al.

This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real-world application scenario, namely the rail surface defects detection task. We collected over 5k high-quality images from railways across China, and annotated 1100 images with the help from railway experts to identify the most common 13 types of rail defects. The dataset can be used for two settings both with unique challenges, the first is the fully-supervised setting using the 1k+ labeled images for training, fine-grained nature and long-tailed distribution of defect classes makes it hard for visual algorithms to tackle. The second is the semi-supervised learning setting facilitated by the 4k unlabeled images, these 4k images are uncurated containing possible image corruptions and domain shift with the labeled images, which can not be easily tackle by previous semi-supervised learning methods. We believe our dataset could be a valuable benchmark for evaluating robustness and reliability of visual algorithms.

Siwei Yang, Shaozuo Yu, Bingchen Zhao et al.

Visual pattern recognition over agricultural areas is an important application of aerial image processing. In this paper, we consider the multi-modality nature of agricultural aerial images and show that naively combining different modalities together without taking the feature divergence into account can lead to sub-optimal results. Thus, we apply a Switchable Normalization block to our DeepLabV3 segmentation model to alleviate the feature divergence. Using the popular symmetric Kullback Leibler divergence measure, we show that our model can greatly reduce the divergence between RGB and near-infrared channels. Together with a hybrid loss function, our model achieves nearly 10\% improvements in mean IoU over previously published baseline.

Mang Tik Chiu, Xingqian Xu, Kai Wang et al.

The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with our challenge dataset. Around 57 participating teams from various countries compete to achieve state-of-the-art in aerial agriculture semantic segmentation. The Agriculture-Vision Challenge Dataset was employed, which comprises of 21,061 aerial and multi-spectral farmland images. This paper provides a summary of notable methods and results in the challenge. Our submission server and leaderboard will continue to open for researchers that are interested in this challenge dataset and task; the link can be found here.