Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

145 bites

Test yourself: Top 30 intermediate Computer Vision interview questionsMultiple choice, with the correct answer and why it is correct on every question. Free, no sign-in.

Intermediate everything in Computer Vision, page 3

intermediate1 min read

Why U-Net skip connections matter for denoising

Skips carry high-resolution spatial detail from encoder to decoder, preserving fine structure lost in downsampling and easing gradient flow, which lets the model restore detail while removing…

intermediate2 min read

Evaluating generative models with FID versus IS

FID compares Inception feature distributions of real and fake images via Frechet distance between two Gaussians; it uses real data as reference and detects diversity issues, unlike IS which uses no real…

intermediate2 min read

Mode collapse in GAN training

Generator produces few outputs ignoring data diversity, caused by chasing whatever fools the current discriminator; mitigate with minibatch discrimination, unrolled GANs, or Wasserstein loss.

intermediate2 min read

Why ViTs need positional embeddings

Self-attention is permutation invariant so patch order is lost; positional embeddings restore spatial location. CNNs encode position implicitly via the fixed convolution grid.

intermediate1 min read

Cross-attention for visual question answering

In cross-attention queries come from one modality and keys/values from the other, e.g. text queries attend over image features so the question selects relevant regions.

intermediate2 min read

How Swin Transformer achieves linear attention

Swin computes attention within local non-overlapping windows of fixed size, making cost linear in patches, then shifts windows between layers so information crosses boundaries.

intermediate1 min read

Inductive biases of ViT versus CNN

CNNs bake in locality and translation equivariance; a plain ViT has almost none beyond patch structure, so it must learn spatial relations from data, needing large datasets or strong pretraining.

intermediate1 min read

Re-identification in multi-object tracking

Re-ID matches an object to its prior id using appearance embeddings, not just position; store track features and match re-entering detections by embedding similarity.

intermediate1 min read

3D CNNs vs two-stream action recognition

3D CNNs learn spatiotemporal filters end to end but are heavy; two-stream splits RGB appearance and precomputed optical flow, strong but costly to compute flow.

intermediate1 min read

Kalman filter for bounding-box tracking

State, transition, measurement models, and process plus measurement noise; predict then correct each frame. State holds box position and velocity; measurement is the detected box.

intermediate1 min read

Brightness constancy and small-motion assumptions

Brightness constancy says a point's intensity is invariant under motion; small motion lets you linearize via Taylor expansion.

intermediate1 min read

How to improve coarse segmentation boundaries?

Skip connections and higher-resolution features, boundary-aware losses, and point-based or CRF refinement.

intermediate1 min read

How does Mask R-CNN do instance segmentation?

Faster R-CNN backbone plus RPN, then RoIAlign and a parallel mask head predicting per-class binary masks.

intermediate1 min read

U-Net architecture and its skip connections

U-Net has a contracting encoder, an expanding decoder, and skip connections that concatenate matching-resolution encoder features into the decoder to recover spatial detail lost in downsampling.

intermediate1 min read

Uses of the 1x1 convolution

A 1x1 conv is a per-pixel linear combination across channels; it reshapes channel depth cheaply and adds nonlinearity. Uses: dimensionality reduction in bottlenecks and channel mixing.

intermediate1 min read

Receptive fields in convolutional networks

Receptive field is the input region affecting a neuron; it grows with depth, larger kernels, and stride. It matters for capturing context in detection and segmentation.

intermediate1 min read

ResNet residual blocks and the degradation problem

A residual block learns F(x) and adds the identity input x, so layers fit a residual; this eases gradient flow and solves the degradation problem.

intermediate1 min read

Regularization techniques for an overfitting CNN

Data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.

intermediate1 min read

The PnP problem in Structure from Motion

PnP recovers a camera's pose from known 3D points and their 2D projections; it registers new frames against the existing point cloud in SfM.

intermediate2 min read

Incremental Structure from Motion pipeline

Detect and match features, estimate two-view geometry, triangulate, then incrementally add images with PnP and refine via bundle adjustment.

We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.

See open roles