Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit harmful content or produce inaccurate evaluations. Therefore, we found that existing benchmarks have low levels of harmfulness, ambiguous data, and limited diversity in image-text pair combinations. To address these issues, we propose the ELITE benchmark, a high-quality safety evaluation benchmark for VLMs, underpinned by our enhanced evaluation method, the ELITE evaluator. The ELITE evaluator explicitly incorporates a toxicity score to accurately assess harmfulness in multimodal contexts, where VLMs often provide specific, convincing, but unharmful descriptions of images. We filter out ambiguous and low-quality image-text pairs from existing benchmarks using the ELITE evaluator and generate diverse combinations of safe and unsafe image-text pairs. Our experiments demonstrate that the ELITE evaluator achieves superior alignment with human evaluations compared to prior automated methods, and the ELITE benchmark offers enhanced benchmark quality and diversity. By introducing ELITE, we pave the way for safer, more robust VLMs, contributing essential tools for evaluating and mitigating safety risks in real-world applications.

In vision transformers, position embedding (PE) plays a crucial role in capturing the order of tokens. However, in vision transformer structures, there is a limitation in the expressiveness of PE due to the structure where position embedding is simply added to the token embedding. A layer-wise method that delivers PE to each layer and applies independent Layer Normalizations for token embedding and PE has been adopted to overcome this limitation. In this paper, we identify the conflicting result that occurs in a layer-wise structure when using the global average pooling (GAP) method instead of the class token. To overcome this problem, we propose MPVG, which maximizes the effectiveness of PE in a layer-wise structure with GAP. Specifically, we identify that PE counterbalances token embedding values at each layer in a layer-wise structure. Furthermore, we recognize that the counterbalancing role of PE is insufficient in the layer-wise structure, and we address this by maximizing the effectiveness of PE through MPVG. Through experiments, we demonstrate that PE performs a counterbalancing role and that maintaining this counterbalancing directionality significantly impacts vision transformers. As a result, the experimental results show that MPVG outperforms existing methods across vision transformers on various tasks.

Post-training quantization (PTQ) is an efficient model compression technique that quantizes a pretrained full-precision model using only a small calibration set of unlabeled samples without retraining. PTQ methods for convolutional neural networks (CNNs) provide quantization results comparable to full-precision counterparts. Directly applying them to vision transformers (ViTs), however, incurs severe performance degradation, mainly due to the differences in architectures between CNNs and ViTs. In particular, the distribution of activations for each channel vary drastically according to input instances, making PTQ methods for CNNs inappropriate for ViTs. To address this, we introduce instance-aware group quantization for ViTs (IGQ-ViT). To this end, we propose to split the channels of activation maps into multiple groups dynamically for each input instance, such that activations within each group share similar statistical properties. We also extend our scheme to quantize softmax attentions across tokens. In addition, the number of groups for each layer is adjusted to minimize the discrepancies between predictions from quantized and full-precision models, under a bit-operation (BOP) constraint. We show extensive experimental results on image classification, object detection, and instance segmentation, with various transformer architectures, demonstrating the effectiveness of our approach.

Training-free network architecture search (NAS) aims to discover high-performing networks with zero-cost proxies, capturing network characteristics related to the final performance. However, network rankings estimated by previous training-free NAS methods have shown weak correlations with the performance. To address this issue, we propose AZ-NAS, a novel approach that leverages the ensemble of various zero-cost proxies to enhance the correlation between a predicted ranking of networks and the ground truth substantially in terms of the performance. To achieve this, we introduce four novel zero-cost proxies that are complementary to each other, analyzing distinct traits of architectures in the views of expressivity, progressivity, trainability, and complexity. The proxy scores can be obtained simultaneously within a single forward and backward pass, making an overall NAS process highly efficient. In order to integrate the rankings predicted by our proxies effectively, we introduce a non-linear ranking aggregation method that highlights the networks highly-ranked consistently across all the proxies. Experimental results conclusively demonstrate the efficacy and efficiency of AZ-NAS, outperforming state-of-the-art methods on standard benchmarks, all while maintaining a reasonable runtime cost.

We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest. The key challenge is to learn person representations robust to intra-class variations, as different persons can have the same attribute and the same person's appearance looks different with viewpoint changes. Recent reID methods focus on learning discriminative features but robust to only a particular factor of variations (e.g., human pose) and this requires corresponding supervisory signals (e.g., pose annotations). To tackle this problem, we propose to disentangle identity-related and -unrelated features from person images. Identity-related features contain information useful for specifying a particular person (e.g.,clothing), while identity-unrelated ones hold other factors (e.g., human pose, scale changes).