Improving semantic grounding in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an orthogonal direction and explore self-correction in VLMs focusing on semantic grounding. We find that VLMs can correct their own semantic grounding mistakes when properly prompted and framed for the task, without any fine-tuning or even access to oracle feedback. We also introduce a self-correction framework in an iterative setting which consistently improves performance across all models investigated. Overall, we show that iterative self-correction consistently improves VLM performance in semantic grounding by up to 8.4 accuracy points across all models investigated, without requiring fine-tuning, additional architectural changes, or external data. Our exploration of self-correction also reveals that, even after several rounds of feedback, strong models like GPT-4V and GPT-4o retain limited capability in leveraging oracle feedback, suggesting promising directions for further research.

Despite recent advances demonstrating vision- language models’ (VLMs) abilities to describe complex relationships among objects in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark of 241 questions across five categories specifically designed for quantitative spatial reasoning, and systematically investigate the performance of SoTA VLMs on this task. Our analysis reveals that questions involving reasoning about distances between objects are particularly challenging for SoTA VLMs; however, some VLMs perform significantly better at this task than others, with an almost 40 points gap between the two best performing models. We also make the surprising observation that the success rate of the top-performing VLM increases by 19 points when a reasoning path using a reference object emerges naturally in the response. Inspired by this observation, we develop a zero-shot prompting technique, SpatialPrompt, that encourages VLMs to answer quantitative spatial questions using references objects as visual cues. Specifically, we demonstrate that instruct- ing VLMs to use reference objects in their reasoning paths significantly improves their quantitative spatial reasoning performance, bypassing the need for external data, architectural modifications, or fine-tuning. Remarkably, by solely using SpatialPrompt, Gemini 1.5 Pro, GPT-4V, and GPT-4o improve by 56.2, 28.5, and 6.7 points on average in Q-Spatial Bench without the need for more data, model architectural modifications, or fine-tuning.

In object detection, varying annotation protocols across datasets can result in annotation mismatches, leading to inconsistent class labels and bounding regions. Addressing these mismatches typically involves manually identifying common trends and fixing the corresponding bounding boxes and class labels. To alleviate this laborious process, we introduce the label transfer problem in object detection. Here, the goal is to transfer bounding boxes from one or more source datasets to match the annotation style of a target dataset. We propose a data-centric approach, Label-Guided Pseudo-Labeling (LGPL), that improves downstream detectors in a manner agnostic to the detector learning algorithms and model architectures. Validating across four object detection scenarios, defined over seven different datasets and three different architectures, we show that transferring labels for a target task via LGPL consistently improves the downstream detection in every setting, on average by $1.88$ mAP and 2.65 AP$^{75}$. Most importantly, we find that when training with multiple labeled datasets, carefully addressing annotation mismatches with LGPL alone can improve downstream object detection better than off-the-shelf supervised domain adaptation techniques that align instance features.

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation strategies for collecting multi-class classification labels for a large collection of images. While methods that exploit learnt models for labeling exist, a surprisingly prevalent approach is to query humans for a fixed number of labels per datum and aggregate them, which is expensive. Building on prior work on online joint probabilistic modeling of human annotations and machine-generated beliefs, we propose modifications and best practices aimed at minimizing human labeling effort. Specifically, we make use of advances in self-supervised learning, view annotation as a semi-supervised learning problem, identify and mitigate pitfalls and ablate several key design choices to propose effective guidelines for labeling. Our analysis is done in a more realistic simulation that involves querying human la-belers, which uncovers issues with evaluation using existing worker simulation methods. Simulated experiments on a 125k image subset of the ImageNet100 show that it can be annotated to 80% top-1 accuracy with 0.35 annotations per image on average, a 2.7x and 6.7x improvement over prior work and manual annotation, respectively.1

In order to learn to perform activities from demonstrations or descriptions, agents need to distill what the essence of the given activity is, and how it can be adapted to new environments. In this work, we address the problem: environment-aware program generation. Given a visual demonstration or a description of an activity, we generate program sketches representing the essential instructions and propose a model to flesh these into full programs representing the actions needed to perform the activity under the presented environmental constraints. To this end, we build upon VirtualHome, to create a new dataset VirtualHome-Env, where we collect program sketches to represent activities and match programs with environments that can afford them. Furthermore, we construct a knowledge base to sample realistic environments and another knowledge base to seek out the programs under the sampled environments. Finally, we propose RNN-ResActGraph, a network that generates a program from a given sketch and an environment graph and tracks the changes in the environment induced by the program.

We propose a scalable approach to learn video-based question answering (QA): to answer a free-form natural language question about the contents of a video. Our approach automatically harvests a large number of videos and descriptions freely available online. Then, a large number of candidate QA pairs are automatically generated from descriptions rather than manually annotated. Next, we use these candidate QA pairs to train a number of video-based QA methods extended from MN (Sukhbaatar et al. 2015), VQA (Antol et al. 2015), SA (Yao et al. 2015), and SS (Venugopalan et al. 2015). In order to handle non-perfect candidate QA pairs, we propose a self-paced learning procedure to iteratively identify them and mitigate their effects in training. Finally, we evaluate performance on manually generated video-based QA pairs. The results show that our self-paced learning procedure is effective, and the extended SS model outperforms various baselines.

Impressive image captioning results are achieved in domains with plenty of training image and sentence pairs (e.g., MSCOCO). However, transferring to a target domain with significant domain shifts but no paired training data (referred to as cross-domain image captioning) remains largely unexplored. We propose a novel adversarial training procedure to leverage unpaired data in the target domain. Two critic networks are introduced to guide the captioner, namely domain critic and multi-modal critic. The domain critic assesses whether the generated sentences are indistinguishable from sentences in the target domain. The multi-modal critic assesses whether an image and its generated sentence are a valid pair. During training, the critics and captioner act as adversaries – captioner aims to generate indistinguishable sentences, whereas critics aim at distinguishing them. The assessment improves the captioner through policy gradient updates. During inference, we further propose a novel critic-based planning method to select high-quality sentences without additional supervision (e.g., tags). To evaluate, we use MSCOCO as the source domain and four other datasets (CUB-200-2011, Oxford-102, TGIF, and Flickr30k) as the target domains. Our method consistently performs well on all datasets. In particular, on CUB-200-2011, we achieve 21.8% CIDEr-D improvement after adaptation. Utilizing critics during inference further gives another 4.5% boost.

We introduce two tactics, namely the strategically-timed attack and the enchanting attack, to attack reinforcement learning agents trained by deep reinforcement learning algorithms using adversarial examples. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of time steps in an episode. Limiting the attack activity to this subset helps prevent detection of the attack by the agent. We propose a novel method to determine when an adversarial example should be crafted and applied. In the enchanting attack, the adversary aims at luring the agent to a designated target state. This is achieved by combining a generative model and a planning algorithm: while the generative model predicts the future states, the planning algorithm generates a preferred sequence of actions for luring the agent. A sequence of adversarial examples is then crafted to lure the agent to take the preferred sequence of actions. We apply the proposed tactics to the agents trained by the state-of-the-art deep reinforcement learning algorithm including DQN and A3C. In 5 Atari games, our strategically-timed attack reduces as much reward as the uniform attack (i.e., attacking at every time step) does by attacking the agent 4 times less often. Our enchanting attack lures the agent toward designated target states with a more than 70% success rate. Example videos are available at http://yclin.me/adversarial_attack_RL/.

Content-addressable memory (CAM) is a hardware table that can compare the search data with all the stored data in parallel. Due to the parallel comparison feature where a large amount of transistors are active on each lookup, however, the power consumption of CAM is usually considerable. This paper presents a hybrid-type CAM design which aims to combine the performance advantage of the NOR-type CAM with the power efficiency of the NAND-type CAM. In our design, a CAM word is divided into two segments, and then all the CAM cells are decoupled from the match line. By minimizing both the match line capacitances and switching activities, our design can largely reduce the power consumption of CAM. The experimental results show that the hybrid-type CAM can reduce the search energy consumption by roughly 89% compared to the traditional NOR-type CAM. Because the hybrid-type CAM provides a fast pull-down path to speed up the lightweight match line discharge, the search performance of our design is even better than that of the traditional NOR-type CAM.

Content addressable memory (CAM) is widely used in many applications that require fast table lookup. Due to the parallel comparison feature and high frequency of lookup, however, the power consumption of CAM is usually significant. In this paper we propose a decoupled match line scheme which combines the performance advantage of the traditional NOR-type CAM and the power efficiency of the traditional NAND-type CAM. In our design, a CAM word is divided into two segments, and then all the CAM cells are decoupled from the match line. By minimizing both the match line capacitances and switching activities, our design can largely reduce the CAM power dissipated in search operations. The results measured from the fabricated chip show that without any performance penalty our design can reduce the search energy consumption of the CAM by 89% compared to the traditional NOR-type CAM design