Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref: (1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended.
The task in referring expression comprehension is to localise the object instance in an image described by a referring expression phrased in natural language. As a language-to-vision matching task, the key to this problem is to learn a discriminative object feature that can adapt to the expression used. To avoid ambiguity, the expression normally tends to describe not only the properties of the referent itself, but also its relationships to its neighbourhood. To capture and exploit this important information we propose a graph-based, language-guided attention mechanism. Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches. Furthermore, the proposed graph attention mechanism enables the comprehension decision to be visualisable and explainable. Experiments on three referring expression comprehension datasets show the advantage of the proposed approach.
In this paper, we propose a novel end-to-end model, namely Single-Stage Grounding network (SSG), to localize the referent given a referring expression within an image. Different from previous multi-stage models which rely on object proposals or detected regions, our proposed model aims to comprehend a referring expression through one single stage without resorting to region proposals as well as the subsequent region-wise feature extraction. Specifically, a multimodal interactor is proposed to summarize the local region features regarding the referring expression attentively. Subsequently, a grounder is proposed to localize the referring expression within the given image directly. For further improving the localization accuracy, a guided attention mechanism is proposed to enforce the grounder to focus on the central region of the referent. Moreover, by exploiting and predicting visual attribute information, the grounder can further distinguish the referent objects within an image and thereby improve the model performance. Experiments on RefCOCO, RefCOCO+, and RefCOCOg datasets demonstrate that our proposed SSG without relying on any region proposals can achieve comparable performance with other advanced models. Furthermore, our SSG outperforms the previous models and achieves the state-of-art performance on the ReferItGame dataset. More importantly, our SSG is time efficient and can ground a referring expression in a 416*416 image from the RefCOCO dataset in 25ms (40 referents per second) on average with a Nvidia Tesla P40, accomplishing more than 9* speedups over the existing multi-stage models.
In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be interpretable to assist users in both development and prediction. Existing models designed to produce interpretable traces of their decision-making process typically require these traces to be supervised at training time. In this paper, we present a novel neural modular approach that performs compositional reasoning by automatically inducing a desired sub-task decomposition without relying on strong supervision. Our model allows linking different reasoning tasks though shared modules that handle common routines across tasks. Experiments show that the model is more interpretable to human evaluators compared to other state-of-the-art models: users can better understand the model's underlying reasoning procedure and predict when it will succeed or fail based on observing its intermediate outputs.
We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our model works on a finer level and embeds fragments of images (objects) and fragments of sentences (typed dependency tree relations) into a common space. In addition to a ranking objective seen in previous work, this allows us to add a new fragment alignment objective that learns to directly associate these fragments across modalities. Extensive experimental evaluation shows that reasoning on both the global level of images and sentences and the finer level of their respective fragments significantly improves performance on image-sentence retrieval tasks. Additionally, our model provides interpretable predictions since the inferred inter-modal fragment alignment is explicit.
In this paper, we address the task of natural language object retrieval, to localize a target object within a given image based on a natural language query of the object. Natural language object retrieval differs from text-based image retrieval task as it involves spatial information about objects within the scene and global scene context. To address this issue, we propose a novel Spatial Context Recurrent ConvNet (SCRC) model as scoring function on candidate boxes for object retrieval, integrating spatial configurations and global scene-level contextual information into the network. Our model processes query text, local image descriptors, spatial configurations and global context features through a recurrent network, outputs the probability of the query text conditioned on each candidate box as a score for the box, and can transfer visual-linguistic knowledge from image captioning domain to our task. Experimental results demonstrate that our method effectively utilizes both local and global information, outperforming previous baseline methods significantly on different datasets and scenarios, and can exploit large scale vision and language datasets for knowledge transfer.
Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer. The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer introduces a reward function to guide sampling of more discriminative expressions. The listener-speaker modules are trained jointly in an end-to-end learning framework, allowing the modules to be aware of one another during learning while also benefiting from the discriminative reinforcer's feedback. We demonstrate that this unified framework and training achieves state-of-the-art results for both comprehension and generation on three referring expression datasets. Project and demo page: https://vision.cs.unc.edu/refer
Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so easily delineated, however. In many of these cases natural language dialog is a natural way to specify the subject of interest, and the task achieving this capability (a.k.a, Referring Expression Comprehension) has recently attracted attention. To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs. The PLAN network has two attention mechanisms that relate parts of the expressions to both the global visual content and also directly to object candidates. Furthermore, the attention mechanisms are recurrent, making the referring process visualizable and explainable. The attended information from these dual sources are combined to reason about the referred object. These two attention mechanisms can be trained in parallel and we find the combined system outperforms the state-of-art on several benchmarked datasets with different length language input, such as RefCOCO, RefCOCO+ and GuessWhat?!.
In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. This allows us to flexibly adapt to expressions containing different types of information in an end-to-end framework. In our model, which we call the Modular Attention Network (MAttNet), two types of attention are utilized: language-based attention that learns the module weights as well as the word/phrase attention that each module should focus on; and visual attention that allows the subject and relationship modules to focus on relevant image components. Module weights combine scores from all three modules dynamically to output an overall score. Experiments show that MAttNet outperforms previous state-of-art methods by a large margin on both bounding-box-level and pixel-level comprehension tasks. Demo and code are provided.
We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their interaction, MAC effectively learns to perform iterative reasoning processes that are directly inferred from the data in an end-to-end approach. We demonstrate the model's strength, robustness and interpretability on the challenging CLEVR dataset for visual reasoning, achieving a new state-of-the-art 98.9% accuracy, halving the error rate of the previous best model. More importantly, we show that the model is computationally-efficient and data-efficient, in particular requiring 5x less data than existing models to achieve strong results.
CLIP의 시각 인코더는 전역(global) 이미지 표현만을 생성하므로 영역 수준 작업에서의 활용이 제한됩니다. 기존의 적응 방식들은 시각적 프롬프팅(visual prompting), 입력 마스킹, 또는 인코더 미세조정에 의존하며, 각각 사전학습된 표현을 손상시킵니다. 본 논문에서는 모든 CLIP 매개변수를 동결(frozen) 상태로 유지하는 경량 어댑터 스티어링 접근법인 LAS-CLIP을 제안합니다. 소형 MaskAdapter는 입력 마스크로부터 헤드별, 층별 어텐션 편향을 생성하여 동결된 셀프 어텐션 층에 주입함으로써 어텐션을 대상 영역으로 유도합니다. 결정적으로 백본이 엄격하게 변경되지 않은 상태로 유지되기 때문에, LAS-CLIP은 마스크가 제공되지 않을 때 바닐라 CLIP으로 원활하게 복귀하여 근본적인 제로샷(zero-shot) 능력을 보존합니다. 약 116K~145K개의 학습 가능한 매개변수와 두 대의 T4 GPU에서 100K개의 학습 샘플만으로, LAS-CLIP은 Alpha-CLIP이 수백만 개의 샘플에서 전체 인코더를 미세조정했음에도 불구하고 ImageNet-S 제로샷 분류 및 RefCOCO 지칭 표현 이해(referring expression comprehension)에서 경쟁력 있거나 우수한 결과를 달성합니다. 정성적 분석은 잘못된 마스크가 주어졌을 때와 다운스트림 생성 작업에서 더 강력한 표현 충실도를 추가로 확인해 줍니다. 프로젝트 페이지 링크는 https://github.com/AnhKhoa585/lasclip 입니다.
Weakly supervised referring expression comprehension(WREC) and segmentation(WRES) aim to learn object grounding based on a given expression using weak supervision signals like image-text pairs. While these tasks have traditionally been modeled separately, we argue that they can benefit from joint learning in a multi-task framework. To this end, we propose WeakMCN, a novel multi-task collaborative network that effectively combines WREC and WRES with a dual-branch architecture. Specifically, the WREC branch is formulated as anchor-based contrastive learning, which also acts as a teacher to supervise the WRES branch. In WeakMCN, we propose two innovative designs to facilitate multi-task collaboration, namely Dynamic Visual Feature Enhancement(DVFE) and Collaborative Consistency Module(CCM). DVFE dynamically combines various pre-trained visual knowledge to meet different task requirements, while CCM promotes cross-task consistency from the perspective of optimization. Extensive experimental results on three popular REC and RES benchmarks, i.e., RefCOCO, RefCOCO+, and RefCOCOg, consistently demonstrate performance gains of WeakMCN over state-of-the-art single-task alternatives, e.g., up to 3.91% and 13.11% on RefCOCO for WREC and WRES tasks, respectively. Furthermore, experiments also validate the strong generalization ability of WeakMCN in both semi-supervised REC and RES settings against existing methods, e.g., +8.94% for semi-REC and +7.71% for semi-RES on 1% RefCOCO. The code is publicly available at https://github.com/MRUIL/WeakMCN.
Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships between visual and linguistic modalities, enabling machines to develop human-like multimodal comprehension capabilities. Consequently, it has extensive applications in various domains. However, since 2021, visual grounding has witnessed significant advancements, with emerging new concepts such as grounded pre-training, grounding multimodal LLMs, generalized visual grounding, and giga-pixel grounding, which have brought numerous new challenges. In this survey, we first examine the developmental history of visual grounding and provide an overview of essential background knowledge. We systematically track and summarize the advancements, and then meticulously define and organize the various settings to standardize future research and ensure a fair comparison. Additionally, we delve into numerous related datasets and applications, and highlight several advanced topics. Finally, we outline the challenges confronting visual grounding and propose valuable directions for future research, which may serve as inspiration for subsequent researchers. By extracting common technical details, this survey encompasses the representative work in each subtopic over the past decade. To the best of our knowledge, this paper represents the most comprehensive overview currently available in the field of visual grounding. This survey is designed to be suitable for both beginners and experienced researchers, serving as an invaluable resource for understanding key concepts and tracking the latest research developments. We keep tracing related work at https://github.com/linhuixiao/Awesome-Visual-Grounding.
UAV 영상에서 텍스트 전용·이미지 전용·텍스트+이미지 쿼리를 모두 지원하고 대상 없음·단일·다중 타깃 그라운딩을 포함하는 범용 참조(Universal Referring) 태스크를 정의하고, 22개 공개 UAV 데이터셋 기반의 멀티모달 벤치마크 UniRef-UAV(15만 건 이상의 쿼리 샘플)와 이종 쿼리를 공유 쿼리 공간으로 매핑하는 탐지 방식 기준선 UAV-URNet을 제안한다. UAV-URNet은 대형 범용 MLLM 대비 더 일관된 대상 없음 판별과 경량화된 재현 가능성을 보이며, 멀티모달 쿼리가 시각적 쿼리 모호성을 줄이고 통합된 쿼리-대상 정렬 공간을 형성함을 실험으로 입증한다.
비전-언어 모델(VLM)은 강력한 원샷(one-shot) 공간 그라운딩을 달성하지만, 자신의 예측을 관찰하고 수정할 수 있는 메커니즘이 없습니다. VLM이 자신의 예측을 렌더링한 시각화를 반복하도록 단순히 프롬프트를 주면 치명적인 실패가 발생함을 발견했습니다: 지시 표현 이해(referring expression comprehension)에서 [email omitted] 79.6%에서 48.7%로 급락(31%p 하락)하여, 그라운딩 능력과 자가 수정 능력 사이의 근본적 격차를 드러냅니다. 우리는 반복적 시각적 사고(IVT)를 제안합니다. 이는 모델이 바운딩 박스를 예측하고, 이미지에 렌더링된 예측을 관찰하며, 시각적 피드백을 통해 반복적으로 정제하는 폐루프(closed-loop) 프레임워크입니다. 2단계 학습 절차가 자가 수정 격차를 해소합니다: 첫째, 기본 모델의 자체 예측을 현실적인 오류로 활용하고 교사 VLM에게 수정 추론 궤적을 생성하도록 프롬프트하여 인간 주석 없이 지도 학습 데이터를 확보합니다. 둘째, 다단계 정제를 안정화하기 위해 단순한 IoU 보상과 함께 그룹 상대 정책 최적화(GRPO)를 적용합니다. RefCOCOg, Ref-Adv, Ref-L4(505개 테스트 샘플)에 걸친 혼합 벤치마크에서 IVT를 적용한 SFT 웜업은 모든 지표에서 원샷 기본 모델을 능가했습니다: [email omitted] 82.0%(+2.4%p), [email omitted] 74.1%(+3.2%p), [email omitted] 48.3%(+2.8%p)로 상승했습니다. GRPO는 단계별 IoU 저하를 5배 더 줄여 정제 궤적을 안정화합니다. 모든 학습은 단일 GPU에서 2,400개 샘플만 사용하며, 공간 자가 수정이 적은 규모에서도 주입 가능한 학습 가능한 능력임을 입증합니다.