CLIP Can Understand Depth

• URL: http://arxiv.org/abs/2402.03251v2
• Date: Wed, 24 Sep 2025 14:59:39 GMT
• Title: CLIP Can Understand Depth
• Authors: Sohee Kim, Jisu Kang, Dunam Kim, Seokju Lee,
• Abstract summary: We show that CLIP can be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data.<n>We distill the semantic prior of its frozen text encoder into a single learnable embedding matrix called "mirror"<n>The resulting model exhibits impressive performance, matching several state-of-the-art vision models on the NYU Depth v2 and KITTI benchmark datasets.
• Score: 6.877245323116022
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper, we demonstrate that CLIP can also be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data, all without requiring fine-tuning. We explore the case of monocular depth estimation, where CLIP's contrastive prior struggles to generalize, compared to its success in domains such as generative modeling and semantic segmentation. Since CLIP fails to consistently capture similarities between image patches and natural language prompts describing distance, we eliminate the use of its pre-trained natural language token embeddings and distill the semantic prior of its frozen text encoder into a single learnable embedding matrix called "mirror". The main design goal of mirror is to derive a non-human language prompt that approximates an optimal natural language prompt: "How far is this location from the camera?" Using this approach, we jointly train two lightweight modules, a mirror and a compact decoder, on top of a frozen CLIP for dense depth prediction. Compared to conventional depth models, our framework is significantly more efficient in terms of parameters and computation. The resulting model exhibits impressive performance, matching several state-of-the-art vision models on the NYU Depth v2 and KITTI benchmark datasets, while outperforming all vision-language depth models based on a frozen CLIP prior. Experiments demonstrate that the suboptimal depth understanding of CLIP in terms of spatial and temporal consistency can be significantly corrected without either fine-tuning it or concatenating mirror with its pre-trained subword token embeddings. Furthermore, an ablation study on the convergence status of mirror shows that it is implicitly trained to capture objects, such as humans and windows, where semantic cues play an important role in detection.

Related papers

• SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation [0.0]
  We present SPACE-CLIP, an architecture that unlocks and interprets latent geometric knowledge directly from a frozen CLIP vision encoder.<n>A semantic pathway interprets high-level features, dynamically conditioned on global context.<n>A structural pathway extracts fine-grained spatial details from early layers.
  arXiv  Detail & Related papers  (2026-01-25T02:32:01Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• CLIP-IN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions [17.05291662808873]
  We present CLIP-IN, a novel framework that bolsters CLIP's fine-grained perception through two core innovations.<n> Firstly, we leverage instruction-editing datasets, originally designed for image manipulation, as a unique source of hard negative image-text pairs.<n> Secondly, CLIP-IN incorporates long captions, utilizing rotary positional encodings to capture rich semantic context often missed by standard CLIP.
  arXiv  Detail & Related papers  (2025-08-04T11:57:10Z)
• Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study [3.1667055223489786]
  Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks. This study presents a comprehensive analysis of CLIP's performance limitations in multi-object contexts through controlled experiments.
  arXiv  Detail & Related papers  (2025-02-27T07:03:10Z)
• DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment [20.953645420787527]
  We train a CLIP-like model with only a fraction of the computational cost compared to CLIP.<n>We achieve state-of-the-art results in zero-shot classification and open-vocabulary semantic segmentation.
  arXiv  Detail & Related papers  (2024-12-20T20:46:48Z)
• CLIP with Quality Captions: A Strong Pretraining for Vision Tasks [16.208506912410147]
  We show that CLIP pretraining with good quality captions can surpass recent supervised, self-supervised and weakly supervised pretraining methods. We find that mobile architectures also benefit significantly from CLIP pretraining.
  arXiv  Detail & Related papers  (2024-05-14T19:06:24Z)
• LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models [45.672539931681065]
  We propose a multi-level interaction paradigm for training lightweight CLIP models. An auxiliary fusion module injecting unmasked image embedding into masked text embedding is proposed.
  arXiv  Detail & Related papers  (2023-12-01T15:54:55Z)
• Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation [31.34615135846137]
  We propose a few-shot-based method which learns to adapt the Vision-Language Models for monocular depth estimation. Specifically, it assigns different depth bins for different scenes, which can be selected by the model during inference. With only one image per scene for training, our extensive experiment results on the NYU V2 and KITTI dataset demonstrate that our method outperforms the previous state-of-the-art method by up to 10.6% in terms of MARE.
  arXiv  Detail & Related papers  (2023-11-02T06:56:50Z)
• SILC: Improving Vision Language Pretraining with Self-Distillation [113.50400246862056]
  We introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation.
  arXiv  Detail & Related papers  (2023-10-20T08:44:47Z)
• Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition [77.93678598476149]
  We establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical structure is built with an image-to-text feature flow. Extensive experiments demonstrate the effectiveness of CLIP-OCR with 93.8% average accuracy on six popular STR benchmarks.
  arXiv  Detail & Related papers  (2023-10-08T04:00:20Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning [14.496173899477283]
  We study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts. We propose to insert adapters, a parameter-efficient technique proven to be effective among large language models, into each CLIP encoder layer. We further equip adapters with concept awareness so that concept-specific features of "object", "attribute", and "composition" can be extracted.
  arXiv  Detail & Related papers  (2023-05-26T07:02:57Z)
• CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model [55.321010757641524]
  We introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP. We scale CLIP4STR in terms of the model size, pre-training data, and training data, achieving state-of-the-art performance on 11 STR benchmarks.
  arXiv  Detail & Related papers  (2023-05-23T12:51:20Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)
• Prompt-based Learning for Unpaired Image Captioning [86.44188293709307]
  Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability.
  arXiv  Detail & Related papers  (2022-05-26T03:13:43Z)
• A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model [61.58071099082296]
  It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2021-12-29T18:56:18Z)
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [91.56988987393483]
  We present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones.
  arXiv  Detail & Related papers  (2021-12-02T18:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.