DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction

• URL: http://arxiv.org/abs/2511.16991v1
• Date: Fri, 21 Nov 2025 06:57:33 GMT
• Title: DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction
• Authors: Jonathan Skaza, Parsa Madinei, Ziqi Wen, Miguel Eckstein,
• Abstract summary: We propose a vision-only model that fuses self-supervised and convolutional representations to predict image complexity.<n>DReX achieves state-of-the-art performance on the IC9600 benchmark.<n>Our findings suggest that visual features alone can be sufficient for human-aligned complexity prediction.
• Score: 1.771934382051849
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual complexity prediction is a fundamental problem in computer vision with applications in image compression, retrieval, and classification. Understanding what makes humans perceive an image as complex is also a long-standing question in cognitive science. Recent approaches have leveraged multimodal models that combine visual and linguistic representations, but it remains unclear whether language information is necessary for this task. We propose DReX (DINO-ResNet Fusion), a vision-only model that fuses self-supervised and convolutional representations through a learnable attention mechanism to predict image complexity. Our architecture integrates multi-scale hierarchical features from ResNet-50 with semantically rich representations from DINOv3 ViT-S/16, enabling the model to capture both low-level texture patterns and high-level semantic structure. DReX achieves state-of-the-art performance on the IC9600 benchmark (Pearson r = 0.9581), surpassing previous methods--including those trained on multimodal image-text data--while using approximately 21.5x fewer learnable parameters. Furthermore, DReX generalizes robustly across multiple datasets and metrics, achieving superior results on Pearson and Spearman correlation, Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Ablation and attention analyses confirm that DReX leverages complementary cues from both backbones, with the DINOv3 [CLS] token enhancing sensitivity to visual complexity. Our findings suggest that visual features alone can be sufficient for human-aligned complexity prediction and that, when properly fused, self-supervised transformers and supervised deep convolutional neural networks offer complementary and synergistic benefits for this task.

Related papers

• Xray-Visual Models: Scaling Vision models on Industry Scale Data [40.21391133092764]
  We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data.<n>Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram.<n>Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2026-02-18T22:22:44Z)
• Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders [74.72147962028265]
  Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet.<n>We investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation.
  arXiv  Detail & Related papers  (2026-01-22T18:58:16Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Describe-to-Score: Text-Guided Efficient Image Complexity Assessment [5.744778242421451]
  Accurately assessing image complexity (IC) is critical for computer vision.<n>We introduce vision-text fusion for IC modeling.<n>We propose the D2S (Describe-to-Score) framework, which generates image captions with a pre-trained vision-language model.
  arXiv  Detail & Related papers  (2025-09-20T10:17:25Z)
• Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction [0.0]
  We introduce the Scale-Interaction Transformer (SIT), a novel hybrid deep learning architecture that synergizes the feature extraction power of CNNs with the relational modeling capabilities of Transformers.<n>We conduct extensive experiments on the widely-used SCUT-FBP5500 benchmark dataset, where the proposed SIT model establishes a new state-of-the-art.<n>Our findings demonstrate that explicitly modeling the interplay between multi-scale visual cues is crucial for high-performance FBP.
  arXiv  Detail & Related papers  (2025-09-05T13:16:55Z)
• F-INR: Functional Tensor Decomposition for Implicit Neural Representations [7.183424522250937]
  Implicit Representation (INR) has emerged as a powerful tool for encoding discrete signals into continuous, differentiable functions using neural networks.<n>We propose F-INR, a framework that reformulates INR learning through functional decomposition, breaking down high-dimensional tasks into lightweight, axis-specific sub-networks.
  arXiv  Detail & Related papers  (2025-03-27T13:51:31Z)
• TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation [65.65530016765615]
  We propose a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives.<n> TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space.<n>We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity.
  arXiv  Detail & Related papers  (2024-05-27T05:45:51Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration [65.11022516031463]
  We present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction. In this paper, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies. Our presented DIN can be trained end-to-end and applied to various image restoration tasks.
  arXiv  Detail & Related papers  (2020-10-29T15:32:00Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)
• Contextual Encoder-Decoder Network for Visual Saliency Prediction [42.047816176307066]
  We propose an approach based on a convolutional neural network pre-trained on a large-scale image classification task. We combine the resulting representations with global scene information for accurately predicting visual saliency. Compared to state of the art approaches, the network is based on a lightweight image classification backbone.
  arXiv  Detail & Related papers  (2019-02-18T16:15:25Z)

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.